The width and height in mx.sym.contrib.BilinearResize2D must be fixed. What if the shape of out is not fixed? I want to make the output has the same shape with anthor layer. Ps: The input of the network always changes, are there any better solutions except always using infer_shape to predict the shape? I think it will be very slow.
Related Topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
How to implement BilinearResize1D? | 2 | 485 | November 19, 2019 | |
How to make two different sizes of feature map have the same size with bigger size?
|
4 | 1039 | March 23, 2018 | |
MXPredReshape always fails (return -1) - MXNet 1.3.0 c++ | 4 | 1068 | October 12, 2018 | |
How cant i get hidden layers shape | 0 | 400 | November 26, 2019 | |
Symbol.infer_shape assertion error on pre-trained MNIST model | 1 | 1035 | July 25, 2018 |